Product
Help
Pricing
About
Jobs
Log in
Get started
Author
Add to collection
Shusheng Xu
Observed name:
Xu, Shusheng
Institution:
Ant Group (China)
Observed institutions:
Ant Group (China),
Tsinghua University
OpenAlex ID:
A5124923808
Is DPO Superior to PPO for LLM Alignment? A Comprehensive Study
2024
·
Xu, Shusheng
, Fu, Wei
, et al.
·
arXiv (Cornell University)
·
213
PDF
AREAL-DTA: Dynamic Tree Attention for Efficient Reinforcement Learning of Large Language Models
2026
·
Zhang, Jiarui
, Yang, Yuchen
, et al.
·
arXiv (Cornell University)
·
4
PDF
When Personal Memory Has No Single Answer: Evaluating LLM Agents under Irreducible Conflict
2026
·
Yang, Lu
, Xu, Shusheng
, et al.
·
arXiv (Cornell University)
·
1
PDF
Parason: Revealing Subtask and Trial Parallelism in LLM Reasoning
2026
·
Zhang, Zhengyang
, Zhang, Zijian
, et al.
·
arXiv (Cornell University)
PDF
Show more works
View as search
Works count:
4
Citation count:
218
H-index:
2
I10-index:
1
Year
Topic
Type
